INDEX

Explanations

information related to percentage change and numerical values

oai_token-act-pair · gpt-3.5-turbo

phrases related to statistical or numerical data trends

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 bona

-0.68

ella

-0.64

radio

-0.62

QB

-0.62

ç«

-0.61

\<

-0.60

monitor

-0.60

tracks

-0.59

abilities

-0.59

asis

-0.59

POSITIVE LOGITS

pees

0.78

 total

0.73

 average

0.64

Downloadha

0.64

 overall

0.63

 APPLIC

0.63

 Orbit

0.62

 potatoes

0.61

verts

0.61

 economy

0.60

Activations Density 0.269%

information related to percentage change and numerical values

phrases related to statistical or numerical data trends

No Comments

No Known Activations